Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names of characters, places, or other significant entities in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ader
    -0.19
    ãĤ¯ãĤ»
    -0.15
    adin
    -0.15
    ãĥªãĥ³ãĤ°
    -0.14
    ouro
    -0.14
    170
    -0.14
     件
    -0.14
    ç·Ĵ
    -0.14
    /runtime
    -0.13
    аÑĢÑĮ
    -0.13
    POSITIVE LOGITS
    mm
    0.16
    /
    0.16
    AVIS
    0.15
     Golden
    0.15
    ides
    0.15
    ors
    0.14
    omination
    0.14
    Golden
    0.14
     squeez
    0.14
    OMATIC
    0.14
    Act Density 0.532%

    No Known Activations